OpenAINot yet certifiedReleased 07/09/2026

gpt-realtime-2.1

GPT-Realtime-2.1 updates GPT-Realtime-2 with improved alphanumeric recognition, silence and noise handling, and interruption behavior. It supports speech-to-speech interactions with configurable reasoning effort, instruction following, and tool use for complex voice-agent workflows.

View API reference ↓
Input / output priceFrom$4.00 / $24.00per 1M
24h uptime—

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "openai/gpt-realtime-2.1",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
OpenAI128K32K——$4.00$24.00Read $0.40Write ——NoYesGlobalListed

Uptime

24 hours

Request success rate per provider.

OpenAI—

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "openai/gpt-realtime-2.1",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. openai/gpt-realtime-2.1. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. gpt-realtime-2.1 supports up to 32,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
Supportedmax_tokenstemperaturestopreasoninginclude_reasoning

Input limits

InputSourcesLimits
Text—Prompt and response share the 128K-token context window

More models by OpenAI

ModelContextInputOutputCacheRelease
openai/gpt-live-10——Read —Write —09/10/2026
openai/gpt-realtime-20$4.00$24.00Read $0.40Write —05/07/2026
openai/gpt-realtime-1.50$4.00$16.00Read $0.40Write —02/23/2026
openai/gpt-realtime-mini0$0.60$2.40Read $0.060Write —10/10/2025